Skill Harvester

技能采集器

Transform your past work into reusable Claude Code skills automatically.

自动将您的过往工作成果转化为可复用的Claude Code技能。

Overview

概述

The Skill Harvester is a meta-skill that helps you systematically extract reusable patterns, workflows, and expertise from your Claude Code sessions and convert them into well-structured skills that can be shared and reused.

技能采集器是一款元技能，可帮助您系统地从Claude Code会话中提取可复用的模式、工作流和专业知识，将其转化为结构清晰、可共享复用的技能。

When to Use

适用场景

Use this skill when:

Completing a significant project or work session
Identifying repetitive patterns across multiple sessions
Building organizational knowledge repositories
Creating team-wide skill libraries
Documenting complex workflows for future reuse
Converting infrastructure/tooling expertise into skills
After solving complex problems that could help future work

当您遇到以下情况时可使用本技能：

完成重大项目或工作会话时
识别多个会话中的重复模式时
构建组织知识库时
创建团队级技能库时
记录复杂工作流以便未来复用的时候
将基础设施/工具使用专业知识转化为技能时
解决了对未来工作有帮助的复杂问题之后

Skill Harvesting Process

技能采集流程

1. Reflection & Analysis

1. 复盘与分析

Examine recent work:

bash

undefined

检查近期工作：

bash

undefined

Review recent git commits

git log --oneline -20

Analyze file changes

git diff HEAD~10..HEAD --stat

Check which files were most modified

git log --pretty=format: --name-only | sort | uniq -c | sort -rg | head -20


**Identify domains:**
- What technologies were used? (frameworks, languages, tools)
- What problems were solved? (deployment, testing, optimization)
- What patterns emerged? (error handling, API integration, workflow)
- What expertise was developed? (domain knowledge, best practices)

git log --pretty=format: --name-only | sort | uniq -c | sort -rg | head -20


**识别领域：**
- 使用了哪些技术？（框架、语言、工具）
- 解决了哪些问题？（部署、测试、优化）
- 出现了哪些模式？（错误处理、API集成、工作流）
- 沉淀了哪些专业知识？（领域知识、最佳实践）

2. Skill Identification

2. 技能识别

Questions to ask:

Reusability: Could this help in future projects?
Generalizability: Does it apply beyond this specific context?
Complexity: Is it non-trivial enough to warrant a skill?
Value: Would others benefit from this pattern?
Completeness: Can it be documented as a standalone skill?

Skill categories to consider:

Infrastructure: Docker, Kubernetes, cloud platforms, CI/CD
Backend: API design, database optimization, authentication
Frontend: Component patterns, state management, build optimization
DevOps: Deployment strategies, monitoring, automation
Data Engineering: ETL pipelines, data validation, transformation
Security: Auth patterns, encryption, vulnerability scanning
Testing: Test strategies, mocking, coverage analysis
Documentation: API docs, architecture diagrams, runbooks

需要明确的问题：

可复用性：这项技能对未来的项目是否有帮助？
通用性：它是否适用于当前特定场景之外的场景？
复杂度：它是否具备足够的价值，值得被封装为独立技能？
价值：其他开发者是否能从该模式中受益？
完整性：它是否可以被作为独立技能进行文档化？

可考虑的技能分类：

基础设施：Docker、Kubernetes、云平台、CI/CD
后端：API设计、数据库优化、鉴权
前端：组件模式、状态管理、构建优化
DevOps：部署策略、监控、自动化
数据工程：ETL管道、数据校验、数据转换
安全：鉴权模式、加密、漏洞扫描
测试：测试策略、Mock、覆盖率分析
文档：API文档、架构图、运行手册

3. Skill Template Creation

3. 技能模板创建

Essential components of a good skill:

markdown

---
name: skill-name (kebab-case)
description: Clear, concise 1-2 sentence description of what the skill does
license: MIT
tags: [relevant, searchable, tags]
---

一个优质技能的核心组成部分：

markdown

---
name: skill-name (kebab-case)
description: Clear, concise 1-2 sentence description of what the skill does
license: MIT
tags: [relevant, searchable, tags]
---

Skill Title

Brief overview paragraph explaining the skill's purpose and value.

When to Use

Specific scenario 1
Specific scenario 2
Specific scenario 3

Specific scenario 1
Specific scenario 2
Specific scenario 3

Core Concepts

Explain the fundamental ideas and principles.

Workflow

Step-by-step process for using the skill.

Step 1: [Action]

Detailed explanation with code examples.

Step 2: [Action]

More details and examples.

Common Patterns

Pattern 1: [Name]

Description and example.

Pattern 2: [Name]

Description and example.

Best Practices

✅ DO

Recommended approach 1
Recommended approach 2

Recommended approach 1
Recommended approach 2

❌ DON'T

Anti-pattern 1
Anti-pattern 2

Anti-pattern 1
Anti-pattern 2

Examples

Example 1: [Scenario]

Full working example with explanation.

Example 2: [Scenario]

Another complete example.

Troubleshooting

Issue 1: [Problem]

Symptoms: What you see Cause: Why it happens Solution: How to fix

Reference

Quick reference table or cheat sheet.

Additional Resources

Links to relevant documentation
Related skills
External references

undefined

Links to relevant documentation
Related skills
External references

undefined

4. Content Extraction

4. 内容提取

Extract from various sources:

bash

undefined

从多个来源提取内容：

bash

undefined

From code files

Look for:

- Complex functions that solve specific problems

- Utility scripts with general applicability

- Configuration patterns that work well

- Error handling strategies

- Integration patterns

From documentation

Harvest:

- README instructions

- Setup guides

- Troubleshooting notes

- Architecture decisions

- Lessons learned

From git commits

git log --all --grep="fix|feat|refactor" --pretty=format:"%h %s" -20

From issue trackers

Extract:

- Common problems and solutions

- Debugging strategies

- Workarounds and fixes

undefined

undefined

5. Skill Organization

5. 技能组织

Directory structure:

harvestable_skills/
├── automation/
│   ├── skill-name/
│   │   └── skill.md
├── backend/
├── devops/
├── frontend/
├── infrastructure/
├── testing/
└── documentation/

Categorization guidelines:

automation: Workflow automation, scripting, batch operations
backend: Server-side development, APIs, databases
cloud: Cloud platforms, serverless, infrastructure
data-engineering: Data processing, ETL, analytics
devops: CI/CD, deployment, monitoring
documentation: Documentation generation, diagrams
frontend: UI development, client-side frameworks
infrastructure: Container orchestration, VMs, networking
security: Authentication, authorization, encryption
testing: Test frameworks, strategies, automation
web-development: Full-stack web development patterns

目录结构：

harvestable_skills/
├── automation/
│   ├── skill-name/
│   │   └── skill.md
├── backend/
├── devops/
├── frontend/
├── infrastructure/
├── testing/
└── documentation/

分类规则：

automation：工作流自动化、脚本开发、批量操作
backend：服务端开发、API、数据库
cloud：云平台、Serverless、基础设施
data-engineering：数据处理、ETL、分析
devops：CI/CD、部署、监控
documentation：文档生成、图表
frontend：UI开发、客户端框架
infrastructure：容器编排、虚拟机、网络
security：身份认证、授权、加密
testing：测试框架、策略、自动化
web-development：全栈Web开发模式

Harvesting Strategies

采集策略

Strategy 1: Domain Expertise Extraction

策略1：领域专业知识提取

When you've worked extensively with a specific tool or technology:

Document the mental model: How does it work? What are the key concepts?
Capture common operations: What do you do most often?
Record gotchas: What are the common pitfalls?
Create quick reference: What do you always look up?

Example domains:

Database query optimization
Docker multi-stage builds
JWT authentication patterns
GraphQL schema design
Terraform module creation

当您在某个特定工具或技术领域有丰富经验时：

记录思维模型：它是如何工作的？核心概念是什么？
梳理常用操作：您最常执行的操作有哪些？
记录常见陷阱：有哪些常见的坑？
创建速查表：哪些内容是你经常需要查询的？

示例领域：

数据库查询优化
Docker多阶段构建
JWT鉴权模式
GraphQL Schema设计
Terraform模块创建

Strategy 2: Workflow Pattern Extraction

策略2：工作流模式提取

When you've developed an effective workflow:

Map the steps: What's the sequence of actions?
Identify decision points: Where are choices made?
Document prerequisites: What's needed to start?
Capture success criteria: How do you know it worked?

Example workflows:

Blue-green deployments
Feature branch review process
Database migration strategies
API versioning approaches

当您沉淀了一套高效的工作流时：

梳理步骤：操作的顺序是什么？
识别决策点：哪些环节需要做选择？
记录前置条件：启动前需要准备什么？
明确成功标准：如何判断操作已生效？

示例工作流：

蓝绿部署
特性分支评审流程
数据库迁移策略
API版本控制方案

Strategy 3: Problem-Solution Pattern Mining

策略3：问题-解决方案模式挖掘

When you've solved complex problems:

Describe the problem: What was broken/missing?
Explain the diagnosis: How did you identify it?
Detail the solution: What fixed it?
Generalize the pattern: How to prevent/solve similar issues?

Example patterns:

Memory leak debugging
Race condition resolution
Performance bottleneck analysis
Security vulnerability patching

当您解决了复杂问题后：

描述问题：什么内容出现了故障/缺失？
说明诊断过程：你是如何定位问题的？
详述解决方案：用什么方法修复了问题？
通用化模式：如何预防/解决同类问题？

示例模式：

内存泄漏调试
竞态条件解决
性能瓶颈分析
安全漏洞补丁

Strategy 4: Tool Mastery Documentation

策略4：工具掌握度文档化

When you've become proficient with a tool:

Core operations: What are the essential commands?
Advanced features: What are the power-user tricks?
Integration patterns: How does it work with other tools?
Troubleshooting: Common errors and fixes?

Example tools:

kubectl for Kubernetes
AWS CLI for cloud operations
jq for JSON processing
git for version control

当您熟练掌握某款工具后：

核心操作：有哪些必备命令？
高级功能：有哪些高阶使用技巧？
集成模式：它如何和其他工具配合使用？
故障排查：常见错误和修复方案是什么？

示例工具：

用于Kubernetes操作的kubectl
用于云操作的AWS CLI
用于JSON处理的jq
用于版本控制的git

Automation Helpers

自动化辅助工具

Bulk Skill Generation

批量技能生成

bash

#!/bin/bash

bash

#!/bin/bash

bulk-harvest.sh - Generate multiple skills from a list

SKILLS_FILE="$1" OUTPUT_DIR="harvestable_skills"

while IFS='|' read -r category name description; do # Skip header and empty lines [[ "$category" == "Category" ]] && continue [[ -z "$category" ]] && continue

SKILL_DIR="$OUTPUT_DIR/$category/$name"
mkdir -p "$SKILL_DIR"

cat > "$SKILL_DIR/skill.md" << EOF

name: $name description: $description license: MIT

SKILLS_FILE="$1" OUTPUT_DIR="harvestable_skills"

while IFS='|' read -r category name description; do # Skip header and empty lines [[ "$category" == "Category" ]] && continue [[ -z "$category" ]] && continue

SKILL_DIR="$OUTPUT_DIR/$category/$name"
mkdir -p "$SKILL_DIR"

cat > "$SKILL_DIR/skill.md" << EOF

name: $name description: $description license: MIT

${name//-/ }

$description

When to Use

TODO: Add specific scenarios

Implementation

TODO: Add implementation details

Examples

TODO: Add working examples

Best Practices

TODO: Add recommendations EOF

echo "✓ Created: $category/$name"

done < "$SKILLS_FILE"


**Usage:**
```bash

TODO: Add recommendations EOF

echo "✓ Created: $category/$name"

done < "$SKILLS_FILE"


**使用方法：**
```bash

Create skills-to-harvest.txt

./bulk-harvest.sh skills-to-harvest.txt

undefined

./bulk-harvest.sh skills-to-harvest.txt

undefined

Git History Analysis

Git历史分析

bash

#!/bin/bash

bash

#!/bin/bash

analyze-work.sh - Analyze recent work for harvestable patterns

echo "=== Most Modified Files ===" git log --since="1 month ago" --pretty=format: --name-only |
sort | uniq -c | sort -rg | head -20

echo "" echo "=== Recent Problem Areas ===" git log --since="1 month ago" --all --grep="fix|bug|issue" --pretty=format:"%h %s" | head -10

undefined

echo "=== Most Modified Files ===" git log --since="1 month ago" --pretty=format: --name-only |
sort | uniq -c | sort -rg | head -20

echo "" echo "=== Recent Problem Areas ===" git log --since="1 month ago" --all --grep="fix|bug|issue" --pretty=format:"%h %s" | head -10

undefined

Quality Checklist

质量检查清单

Integration Workflow

集成工作流

Step 1: Create in Harvestable Directory

步骤1：在待采集目录中创建

bash

mkdir -p harvestable_skills/[category]/[skill-name]

bash

mkdir -p harvestable_skills/[category]/[skill-name]

Create skill.md with full content

undefined

undefined

Step 2: Review and Refine

步骤2：评审与优化

Test all examples
Verify instructions
Add missing sections
Improve clarity

测试所有示例
验证操作指南
补充缺失的章节
提升内容清晰度

Step 3: Move to Skills Collection

步骤3：移动到技能集合

bash

undefined

bash

undefined

Copy to final location

cp -r harvestable_skills/[category]/[skill-name] skills/

Or organize by category

cp -r harvestable_skills/[category]/[skill-name] skills-by-category/[category]/

undefined

cp -r harvestable_skills/[category]/[skill-name] skills-by-category/[category]/

undefined

Step 4: Commit and Share

步骤4：提交与分享

bash

git add skills/ harvestable_skills/
git commit -m "🎯 Harvest skills: [description]"
git push

bash

git add skills/ harvestable_skills/
git commit -m "🎯 Harvest skills: [description]"
git push

Examples of Harvested Skills

已采集技能示例

Example 1: From Infrastructure Work → Skill

示例1：从基础设施工作 → 技能

Original work: Managing Proxmox VE cluster with containers and VMs

Harvested skill:

proxmox-manager

Container lifecycle management
VM provisioning
GPU passthrough configuration
Network troubleshooting
Backup and restore procedures

原始工作：使用容器和虚拟机管理Proxmox VE集群

采集到的技能：

proxmox-manager

容器生命周期管理
虚拟机 provisioning
GPU直通配置
网络故障排查
备份与恢复流程

Example 2: From Problem Solving → Skill

示例2：从问题解决过程 → 技能

Original work: Dealing with Claude Code timeouts during bulk operations

Harvested skill:

session-timeout-handler

Chunking strategies
Checkpoint patterns
Progress tracking
Resume mechanisms
Background process management

原始工作：处理批量操作时的Claude Code超时问题

采集到的技能：

session-timeout-handler

分块策略
检查点模式
进度跟踪
断点续跑机制
后台进程管理

Example 3: From Workflow → Skill

示例3：从工作流 → 技能

Original work: Managing multiple Git repositories with Claude-specific branching

Harvested skill:

claude-git-branching

Branch naming conventions
Push with retry logic
Multi-repo coordination
Conflict resolution
PR automation

原始工作：使用Claude专属的分支规则管理多个Git仓库

采集到的技能：

claude-git-branching

分支命名规范
带重试逻辑的推送
多仓库协同
冲突解决
PR自动化

Tips for Effective Harvesting

高效采集的技巧

🎯 Focus on Value

🎯 聚焦价值

Harvest skills that:

Save significant time
Reduce errors
Encode expertise
Enable new capabilities
Solve recurring problems

优先采集具备以下特点的技能：

能显著节省时间
可减少错误
沉淀了专业知识
能实现新的能力
可解决反复出现的问题

📝 Document Context

📝 记录上下文

Include:

Why this approach works
When to use alternatives
Trade-offs and considerations
Real-world scenarios
Lessons learned

包含以下内容：

该方案有效的原因
何时应该使用替代方案
权衡点和注意事项
真实场景示例
经验教训

🔄 Iterate and Improve

🔄 迭代优化

Start with basic version
Add examples from actual use
Incorporate feedback
Refine based on experience
Version as needed

从基础版本开始
补充实际使用的示例
整合反馈意见
基于使用经验优化
按需进行版本更新

🤝 Share and Collaborate

🤝 分享与协作

Contribute to team repositories
Accept contributions
Review and merge improvements
Build on others' skills
Create skill compositions

贡献到团队仓库
接受他人的贡献
评审并合并优化内容
基于他人的技能进行扩展
创建技能组合

Skill Composition

技能组合

Combine multiple skills for powerful workflows:

markdown

undefined

将多个技能结合可实现更强大的工作流：

markdown

undefined

Example: Full-Stack Deployment Skill

示例：全栈部署技能

Combines:

docker-optimization (build efficient images)
kubernetes-deploy (deploy to cluster)
database-migration (update schema)
health-check-monitoring (verify deployment)
rollback-strategy (revert if needed)

undefined

组合以下技能：

docker-optimization (构建高效镜像)
kubernetes-deploy (部署到集群)
database-migration (更新Schema)
health-check-monitoring (验证部署结果)
rollback-strategy (必要时回滚)

undefined

Measurement and Tracking

度量与追踪

Track the value of your skills:

bash

undefined

追踪技能的价值：

bash

undefined

Track skill usage

echo "$(date): Used skill-harvester for project X" >> ~/.claude/skill-usage.log

Count skill reuse

grep "skill-harvester" ~/.claude/skill-usage.log | wc -l

Measure time saved

Before: 4 hours to set up manually

After: 20 minutes with skill

Savings: 3.67 hours per use

undefined

undefined

Advanced Patterns

高级模式

Pattern 1: Progressive Disclosure

模式1：渐进式展示

Start with simple template, add complexity as needed:

Basic: Essential operations only
Intermediate: Common patterns and variations
Advanced: Edge cases and optimizations
Expert: Deep dives and internals

从简单模板开始，按需逐步增加复杂度：

基础版：仅包含核心操作
中级版：包含常见模式和变体
高级版：包含边缘场景和优化
专家版：深度解析内部原理

Pattern 2: Skill Families

模式2：技能家族

Create related skills that work together:

database-skills/
├── postgres-optimization/
├── postgres-backup/
├── postgres-replication/
└── postgres-monitoring/

创建可协同使用的相关技能：

database-skills/
├── postgres-optimization/
├── postgres-backup/
├── postgres-replication/
└── postgres-monitoring/

Pattern 3: Meta-Skills

模式3：元技能

Skills that help create or manage other skills:

skill-harvester (this skill)
skill-tester (validate skills work)
skill-documenter (generate documentation)
skill-versioner (manage versions)

用于创建或管理其他技能的技能：

skill-harvester (本技能)
skill-tester (验证技能可用性)
skill-documenter (生成文档)
skill-versioner (管理版本)

Resources

资源

Skill Repositories

技能仓库

anthropics/claude-code-skills
Community skill collections
Team-specific repositories

anthropics/claude-code-skills
社区技能集合
团队专属仓库

Tools

工具

Git for version control
Markdown for documentation
YAML for metadata
Shell scripts for automation

用于版本控制的Git
用于文档编写的Markdown
用于元数据的YAML
用于自动化的Shell脚本

Best Practices

最佳实践

Follow Claude Code skill conventions
Use consistent formatting
Include metadata frontmatter
Tag appropriately
Version when needed

Version: 1.0.0 Author: Harvested from your_claude_skills repository Last Updated: 2025-11-18 License: MIT

遵循Claude Code技能规范
使用统一的格式
包含元数据头信息
打上合适的标签
按需进行版本管理

版本：1.0.0 作者：从your_claude_skills仓库采集 最后更新：2025-11-18 许可证：MIT

Quick Start

快速开始

Reflect: Review your recent work (git log, files changed, problems solved)
Identify: List 3-7 skills worth harvesting
Create: Use the skill template for each
Organize: Place in appropriate category
Commit: Add to repository
Share: Push and make available to team

Remember: The best skills solve real problems and encode genuine expertise. Happy harvesting! 🎯

复盘：回顾近期工作（git日志、变更文件、解决的问题）
识别：列出3-7个值得采集的技能
创建：为每个技能使用技能模板生成内容
组织：放置到合适的分类下
提交：添加到仓库
分享：推送到远程仓库，提供给团队使用

请记住： 最好的技能一定是解决真实问题、沉淀了真实专业知识的。祝您采集愉快！🎯

skill-harvester

Original

Translation

Skill Harvester

技能采集器

Overview

概述

When to Use

适用场景

Skill Harvesting Process

技能采集流程

1. Reflection & Analysis

1. 复盘与分析

Review recent git commits

Review recent git commits

Analyze file changes

Analyze file changes

Check which files were most modified

Check which files were most modified

2. Skill Identification

2. 技能识别

3. Skill Template Creation

3. 技能模板创建

Skill Title

Skill Title

When to Use

When to Use

Core Concepts

Core Concepts

Workflow

Workflow

Step 1: [Action]

Step 1: [Action]

Step 2: [Action]

Step 2: [Action]

Common Patterns

Common Patterns

Pattern 1: [Name]

Pattern 1: [Name]

Pattern 2: [Name]

Pattern 2: [Name]

Best Practices

Best Practices

✅ DO

✅ DO

❌ DON'T

❌ DON'T

Examples

Examples

Example 1: [Scenario]

Example 1: [Scenario]

Example 2: [Scenario]

Example 2: [Scenario]

Troubleshooting

Troubleshooting

Issue 1: [Problem]

Issue 1: [Problem]

Reference

Reference

Additional Resources

Additional Resources

4. Content Extraction

4. 内容提取

From code files

From code files

Look for:

Look for:

- Complex functions that solve specific problems

- Complex functions that solve specific problems

- Utility scripts with general applicability

- Utility scripts with general applicability

- Configuration patterns that work well

- Configuration patterns that work well

- Error handling strategies

- Error handling strategies

- Integration patterns

- Integration patterns

From documentation

From documentation

Harvest: